Parrot: Enhancing Multi-Turn Instruction Following for Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909208541134848 |
|---|---|
| author | Sun, Yuchong Liu, Che Zhou, Kun Huang, Jinwen Song, Ruihua Zhao, Wayne Xin Zhang, Fuzheng Zhang, Di Gai, Kun |
| author_facet | Sun, Yuchong Liu, Che Zhou, Kun Huang, Jinwen Song, Ruihua Zhao, Wayne Xin Zhang, Fuzheng Zhang, Di Gai, Kun |
| contents | Humans often interact with large language models (LLMs) in multi-turn interaction to obtain desired answers or more information. However, most existing studies overlook the multi-turn instruction following ability of LLMs, in terms of training dataset, training method, and evaluation benchmark. In this paper, we introduce Parrot, a solution aiming to enhance multi-turn instruction following for LLMs. First, we introduce an efficient but effective method for collecting multi-turn instructions that feature human-like queries, such as anaphora and ellipsis. Second, we propose a context-aware preference optimization strategy to further enhance LLMs for complex queries in multi-turn interaction. Moreover, to quantitatively evaluate LLMs in multi-turn instruction following, we manually build a multi-turn benchmark derived from existing ones. Extensive experiments show that Parrot improves current LLMs by up to 7.2% in multi-turn instruction following. Our dataset and codes will be open-sourced to facilitate future research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_07301 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Parrot: Enhancing Multi-Turn Instruction Following for Large Language Models Sun, Yuchong Liu, Che Zhou, Kun Huang, Jinwen Song, Ruihua Zhao, Wayne Xin Zhang, Fuzheng Zhang, Di Gai, Kun Computation and Language Humans often interact with large language models (LLMs) in multi-turn interaction to obtain desired answers or more information. However, most existing studies overlook the multi-turn instruction following ability of LLMs, in terms of training dataset, training method, and evaluation benchmark. In this paper, we introduce Parrot, a solution aiming to enhance multi-turn instruction following for LLMs. First, we introduce an efficient but effective method for collecting multi-turn instructions that feature human-like queries, such as anaphora and ellipsis. Second, we propose a context-aware preference optimization strategy to further enhance LLMs for complex queries in multi-turn interaction. Moreover, to quantitatively evaluate LLMs in multi-turn instruction following, we manually build a multi-turn benchmark derived from existing ones. Extensive experiments show that Parrot improves current LLMs by up to 7.2% in multi-turn instruction following. Our dataset and codes will be open-sourced to facilitate future research. |
| title | Parrot: Enhancing Multi-Turn Instruction Following for Large Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2310.07301 |